Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    technology-related entities, companies, and products

    oai_token-act-pair · gpt-3.5-turbo

    references to specific technology companies and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wat
    -0.72
    ocious
    -0.72
    itsch
    -0.72
    hemy
    -0.72
    ï¸ı
    -0.71
    âĢİ
    -0.71
    zbollah
    -0.71
    icted
    -0.71
    bender
    -0.71
    ften
    -0.71
    POSITIVE LOGITS
     proprietary
    0.76
     Procedure
    0.75
     Advantage
    0.74
     Edge
    0.72
     Customer
    0.72
     Identity
    0.72
     Account
    0.70
     Reference
    0.70
     Address
    0.70
     Vehicle
    0.69
    Act Density 0.342%

    No Known Activations